{"id":"https://openalex.org/W4372266937","doi":"https://doi.org/10.1109/icassp49357.2023.10096317","title":"Code-Switching Text Generation and Injection in Mandarin-English ASR","display_name":"Code-Switching Text Generation and Injection in Mandarin-English ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266937","doi":"https://doi.org/10.1109/icassp49357.2023.10096317"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027896769","display_name":"Haibin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Haibin Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101942107","display_name":"Yuxuan Hu","orcid":"https://orcid.org/0000-0002-3345-7766"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yuxuan Hu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Corporation","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460574","display_name":"Jin Ma","orcid":"https://orcid.org/0009-0006-7440-6240"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ma Jin","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084708165","display_name":"Linquan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Linquan Liu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328458","display_name":"Yu Shi","orcid":"https://orcid.org/0000-0003-1940-0074"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yu Shi","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["CN","FI"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Microsoft Corporation","Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]},{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569588","display_name":"Edward Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Edward Lin","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089195158","display_name":"Michael Zeng","orcid":"https://orcid.org/0000-0001-5302-5883"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Michael Zeng","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832618951797485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7057299613952637},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5905876159667969},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5759373903274536},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5526328086853027},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5483655333518982},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48242172598838806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4761195778846741},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44432318210601807},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.43501320481300354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42922142148017883},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09122774004936218},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07957568764686584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832618951797485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7057299613952637},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5905876159667969},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5759373903274536},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5526328086853027},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5483655333518982},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48242172598838806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4761195778846741},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44432318210601807},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.43501320481300354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42922142148017883},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09122774004936218},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07957568764686584},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W2782005958","https://openalex.org/W2842511635","https://openalex.org/W2899073901","https://openalex.org/W2939069254","https://openalex.org/W2939757332","https://openalex.org/W2963414781","https://openalex.org/W2964012862","https://openalex.org/W2972417954","https://openalex.org/W3016010032","https://openalex.org/W3096122506","https://openalex.org/W3097306574","https://openalex.org/W3134568285","https://openalex.org/W3160201895","https://openalex.org/W3204123830","https://openalex.org/W3204687321","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209371554","https://openalex.org/W4210690962","https://openalex.org/W4210811812","https://openalex.org/W4223622550","https://openalex.org/W4226120743","https://openalex.org/W4226440507","https://openalex.org/W4287890956","https://openalex.org/W4297808394","https://openalex.org/W6755461288","https://openalex.org/W6802398075","https://openalex.org/W6802465204","https://openalex.org/W6803092890"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Code-switching":[0],"speech":[1,28,64,94,116,151],"refers":[2],"to":[3,35,71,121,158],"a":[4,15,31,69,107],"means":[5],"of":[6,38,53,112,130,149,160],"expression":[7],"by":[8,86,92],"mixing":[9],"two":[10],"or":[11,90],"more":[12,169],"languages":[13],"within":[14],"single":[16],"utterance.":[17],"Automatic":[18],"Speech":[19],"Recognition":[20],"(ASR)":[21],"with":[22,106,172],"End-to-End":[23],"(E2E)":[24],"modeling":[25],"for":[26,49],"such":[27],"can":[29],"be":[30],"challenging":[32],"task":[33],"due":[34],"the":[36,51,102,128,147,164,173],"lack":[37],"data.":[39],"In":[40],"this":[41],"study,":[42],"we":[43],"investigate":[44,78],"text":[45,74,81,96,125,153],"generation":[46],"and":[47,76,95,146,152],"injection":[48],"improving":[50],"performance":[52,129],"an":[54],"industry":[55],"commonly-used":[56],"streaming":[57],"model,":[58],"Transformer-Transducer":[59],"(T-T),":[60],"in":[61],"Mandarin-English":[62,114],"code-switching":[63,124],"recognition.":[65],"We":[66],"first":[67],"propose":[68],"strategy":[70],"generate":[72],"codeswitching":[73],"data":[75,171],"then":[77],"injecting":[79],"generated":[80,123],"into":[82],"T-T":[83,103,131],"model":[84,104],"explicitly":[85],"Text-To-Speech":[87],"(TTS)":[88],"conversion":[89,162],"implicitly":[91],"tying":[93,150],"latent":[97,154],"spaces.":[98],"Experimental":[99],"results":[100],"on":[101,142,163],"trained":[105],"dataset":[108],"containing":[109],"1,800":[110],"hours":[111],"real":[113],"code-switched":[115],"show":[117],"that":[118,159],"our":[119],"approaches":[120],"inject":[122],"significantly":[126],"boost":[127],"models,":[132],"i.e.,":[133],"16%":[134],"relative":[135],"Token-based":[136],"Error":[137],"Rate":[138],"(TER)":[139],"reduction":[140],"averaged":[141],"three":[143],"evaluation":[144,165],"sets,":[145],"approach":[148],"spaces":[155],"is":[156],"superior":[157],"TTS":[161],"set":[166],"which":[167],"contains":[168],"homogeneous":[170],"training":[174],"set.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
